{"id":"W2967741816","doi":"","title":"Social Media Data, Machine Learning and Causal Inference","year":2019,"lang":"en","type":"article","venue":"Journal of the Association for Information Systems","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Social media; Artificial intelligence; Causal inference; Inference; Machine learning; Data science; Natural language processing; World Wide Web; Econometrics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00529416,0.00004791296,0.0001698526,0.00009639373,0.0003961544,0.0002364556,0.0002549597,0.00006863825,0.000008966847],"category_scores_gemma":[0.003538065,0.00003410943,0.0000717389,0.0002180433,0.00001687039,0.001270927,0.00005688244,0.0001445291,0.00001198798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001851334,"about_ca_system_score_gemma":0.0001529659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009957253,"about_ca_topic_score_gemma":0.00008153201,"domain_scores_codex":[0.9983512,0.0003534847,0.000471087,0.0000391421,0.0006845517,0.0001004904],"domain_scores_gemma":[0.9962332,0.001407765,0.001581942,0.00005134983,0.0006909611,0.00003480255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009161518,0.00004124078,0.6325417,0.0001390269,0.000592903,1.617737e-7,0.09354711,0.005401754,0.00005050336,0.2250219,0.01040833,0.0321637],"study_design_scores_gemma":[0.0007767366,0.00002288322,0.03065034,0.00003384827,0.00008875228,0.000002270341,0.007567397,0.01760573,0.000003436591,0.001555995,0.9415847,0.0001079169],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7618545,0.001714517,0.06063929,0.0288233,0.02641363,0.003622184,0.0006000748,0.0002115505,0.1161209],"genre_scores_gemma":[0.9979829,0.00002415356,0.0001984821,0.00004147258,0.0004061038,0.000001392959,0.00002441736,0.000002268179,0.00131882],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9311764,"threshold_uncertainty_score":0.423565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04886245868015036,"score_gpt":0.368742220054924,"score_spread":0.3198797613747736,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}